Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0831050e73045e270c6149ef4017814aa6689592222a62d3abf451d24eea41df
+oid sha256:901f15ae44086fc72a2d2f7c8679089c9bc55730aae7e6870a044d9900ad43bb
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f876c2712215e1fb9cb3bf9babf676425fb8c75b71cd653f94a86460765fcbc
+oid sha256:3f58a8d1158cf9834ffa967091fab1ca6510837b4fd1a9c11181cc457b7888ce
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.369112014770508,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.033098882912701695,
+  "best_metric": 10.368470191955566,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.049648324369052546,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 326.7,
       "eval_steps_per_second": 163.99,
       "step": 20
+    },
+    {
+      "epoch": 0.03475382705833678,
+      "grad_norm": 0.1077900379896164,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.3692,
+      "step": 21
+    },
+    {
+      "epoch": 0.03971865949524204,
+      "grad_norm": 0.09027549624443054,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.3713,
+      "step": 24
+    },
+    {
+      "epoch": 0.04137360364087712,
+      "eval_loss": 10.368561744689941,
+      "eval_runtime": 0.7762,
+      "eval_samples_per_second": 328.514,
+      "eval_steps_per_second": 164.901,
+      "step": 25
+    },
+    {
+      "epoch": 0.04468349193214729,
+      "grad_norm": 0.0892433375120163,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.3677,
+      "step": 27
+    },
+    {
+      "epoch": 0.049648324369052546,
+      "grad_norm": 0.09582661092281342,
+      "learning_rate": 0.0,
+      "loss": 10.3744,
+      "step": 30
+    },
+    {
+      "epoch": 0.049648324369052546,
+      "eval_loss": 10.368470191955566,
+      "eval_runtime": 0.7617,
+      "eval_samples_per_second": 334.774,
+      "eval_steps_per_second": 168.043,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 523024465920.0,
+  "total_flos": 784536698880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null